Every premium and members-only resource for $9.99/month, as a no-commitment subscription. See the plans

PalateKit

Sign in
Menu

Request a resource

Describe the resource you are missing in one sentence. We will email you when it is published.

0 / 280

A page, a video or an image online.

Unlock PalateKit

Unlock everything

Plan

Paying means accepting our terms of sale.

Secure payment by Stripe. Receipts and invoices sent by email.

Welcome back

Sign in to install, download or save this resource. A free account is enough for free resources.

Build and run an AI agent evaluation v1.0.0

Use this resource to build an evaluation of an AI agent or prompt and run it

New

  • 338 downloads
  • 100 likes
  • 189 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install llm-evaluation-build-run

With no option, the skill goes to ~/.agents/skills/; add --agent claude-code (or codex, cursor…) to target an agent.

First time: connect the CLI with

npx --yes palatekit@latest login

The agent starts from real failures, chooses between a test suite and a dataset, gathers cases from traces or synthetic data, then scores with code before adding one judge per failure mode. It then reads the scores back to produce a summary you can act on.

Mostly picked by

Updated November 2, 2026

Card for the “Build and run an AI agent evaluation” skill

Details

Works in
Install guides
Generates with
Your agent's model
Licence
Apache-2.0

Similar resources

View all

What you get

  • references/error-analysis.md: error analysis to ground the cases
  • references/write-judge-prompt.md: writing an LLM judge
  • references/validate-evaluator.md: validating an evaluator against human labels

Good fit for

  • You must measure an agent's quality before shipping it
  • A RAG system answers poorly and you want a numeric evaluation

Not for

    Tags

    • evaluation
    • llm
    • judge
    • rag
    • experiment

    About

    You say

    “Measure the quality of our RAG support assistant on support questions and flag hallucinations.”

    Card for the “Build and run an AI agent evaluation” skill

    Skill published by comet-ml under the Apache-2.0 license, delivered in its original version.

    Show more

    How to use it

    1. Install the skill in your agent's skills folder
    2. Ask your agent to build an evaluation of an AI agent or prompt and run it
    3. Review and adjust the result

    Content preview

    Files

    • LICENSE11.1 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • references/error-analysis.md8.1 KB
    • references/eval-audit.md8.8 KB
    • references/evaluate-rag.md4.7 KB
    • references/generate-synthetic-data.md5.6 KB
    • references/validate-evaluator.md8 KB
    • references/write-judge-prompt.md7.8 KB
    • SKILL.md12.6 KB

    Origin and licence

    Listed unmodified

    Author
    comet-ml
    Source
    github.com/comet-ml/opik-skills/tree/f0fb8b9e6439c71e8ab88f1643bcf52ef68173c5/skills/opik-evaluate
    Licence
    Apache-2.0

    Notice

    « opik-evaluate » (comet-ml, Apache-2.0) livré dans sa version d'origine : fiche en français et en anglais par PalateKit.

    User reviews

    –

    No ratings yet

    Loading reviews…

    Delete your review?

    Your rating and comment will be removed from the page.